Publications related to Learning Search Strategies from Human Demonstrations

Reinforcement learning of trajectory distributions: Applications in assisted teleoperation and motion planning

The majority of learning from demonstration approaches do not address suboptimal demonstrations or cases when drastic changes in the environment occur after the demonstrations were made. For example, in real teleoperation tasks, the demonstrations provided ...

2019

Learning Trajectory Distributions for Assisted Teleoperation and Path Planning

Several approaches have been proposed to assist humans in co-manipulation and teleoperation tasks given demonstrated trajectories. However, these approaches are not applicable when the demonstrations are suboptimal or when the generalization capabilities o ...

2019

A survey on policy search algorithms for learning robot controllers in a handful of trials

Sylvain Calinon

Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only a handf ...

2019

Manifold Learning and Optimal Control for Obstacle Avoidance in Autonomous Driving

Colin Neil Jones, Sanket Sanjay Diwale

A novel manifold learning approach is presented to incorporate computationally efficient obstacle avoidance constraints in optimal control algorithms. The method presented provides a significant computational benefit by reducing the number of constraints r ...

2019

MAMUT: Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-User Video Transcoding

David Atienza Alonso, Marina Zapater Sancho, Luis Maria Costero Valero, Arman Iranfar

Real-time video transcoding has recently raised as a valid alternative to address the ever-increasing demand for video contents in servers' infrastructures in current multi-user environments. High Efficiency Video Coding (HEVC) makes efficient online trans ...

IEEE2019

A simple landscape of metastable state energies for two-dimensional cellular matter

Sangwoo Kim

The mechanical behavior of cellular matter in two dimensions can be inferred from geometric information near its energetic ground state. Here it is shown that the much larger set of all metastable state energies is universally described by a systematic exp ...

2019

Generative Models for Learning Robot Manipulation Skills from Humans

Ajay Kumar Tanwani

A long standing goal in artificial intelligence is to make robots seamlessly interact with humans in performing everyday manipulation skills. Learning from demonstrations or imitation learning provides a promising route to bridge this gap. In contrast to d ...

EPFL2018

Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models

Sylvain Calinon, Ajay Kumar Tanwani, Swati Krishnan

Generalizing manipulation skills to new situations requires extracting invariant patterns from demonstrations. For example, the robot needs to understand the demonstrations at a higher level while being invariant to the appearance of the objects, geometric ...

2018

Incorporating Human Expertise in Robot Motion Learning and Synthesis

Hang Yin

With the exponential growth of robotics and the fast development of their advanced cognitive and motor capabilities, one can start to envision humans and robots jointly working together in unstructured environments. Yet, for that to be possible, robots nee ...

EPFL2018

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

Fei Pu

In this thesis, we study systems of linear and/or non-linear stochastic heat equations and fractional heat equations in spatial dimension

1

driven by space-time white noise. The main topic is the study of hitting probabilities for the solutions to these ...

EPFL2018

Learning Search Strategies from Human Demonstrations

Graph Chatbot

Chat with Graph Search

Reinforcement learning of trajectory distributions: Applications in assisted teleoperation and motion planning

Learning Trajectory Distributions for Assisted Teleoperation and Path Planning

A survey on policy search algorithms for learning robot controllers in a handful of trials

Manifold Learning and Optimal Control for Obstacle Avoidance in Autonomous Driving

MAMUT: Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-User Video Transcoding

A simple landscape of metastable state energies for two-dimensional cellular matter

Generative Models for Learning Robot Manipulation Skills from Humans

Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models

Incorporating Human Expertise in Robot Motion Learning and Synthesis

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

A survey on policy search algorithms for learning robot controllers in a handful of trials

Generative Models for Learning Robot Manipulation Skills from Humans

Reinforcement learning of trajectory distributions: Applications in assisted teleoperation and motion planning

Incorporating Human Expertise in Robot Motion Learning and Synthesis

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

Learning Trajectory Distributions for Assisted Teleoperation and Path Planning

Manifold Learning and Optimal Control for Obstacle Avoidance in Autonomous Driving

Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models

A simple landscape of metastable state energies for two-dimensional cellular matter

MAMUT: Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-User Video Transcoding